{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OVS3DCC6MMIOOX3NLEIS5V74PO","short_pith_number":"pith:OVS3DCC6","schema_version":"1.0","canonical_sha256":"7565b1885e6310e75f6d59112ed7fc7b83b8a303eebc248ac32ab31ee83d7b8b","source":{"kind":"arxiv","id":"2412.17092","version":1},"attestation_state":"computed","paper":{"title":"SAIL: Sample-Centric In-Context Learning for Document Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jinyu Zhang, Jize Wang, Xinyi Le, Zhiyuan You","submitted_at":"2024-12-22T16:58:59Z","abstract_excerpt":"Document Information Extraction (DIE) aims to extract structured information from Visually Rich Documents (VRDs). Previous full-training approaches have demonstrated strong performance but may struggle with generalization to unseen data. In contrast, training-free methods leverage powerful pre-trained models like Large Language Models (LLMs) to address various downstream tasks with only a few examples. Nonetheless, training-free methods for DIE encounter two primary challenges: (1) understanding the complex relationship between layout and textual elements in VRDs, and (2) providing accurate gu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.17092","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T16:58:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd5ecbfee38d434963949c620412a4c8c2d66daf0d85f8e7402dd57e8d4203a2","abstract_canon_sha256":"c4aff696c59acfebf1921274ee1de4aae0e3c3136ef4eb9beaaa2ef538d3b9db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:17.613187Z","signature_b64":"KLTMyPTVnmBhR0du2yCTQRr4k5Uyj4cC2xVmBDuuLj/TMERDvPpk0e6QduzokDfrCNdxhU0TpSlSkzhHE3UkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7565b1885e6310e75f6d59112ed7fc7b83b8a303eebc248ac32ab31ee83d7b8b","last_reissued_at":"2026-07-05T09:53:17.612733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:17.612733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAIL: Sample-Centric In-Context Learning for Document Information Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jinyu Zhang, Jize Wang, Xinyi Le, Zhiyuan You","submitted_at":"2024-12-22T16:58:59Z","abstract_excerpt":"Document Information Extraction (DIE) aims to extract structured information from Visually Rich Documents (VRDs). Previous full-training approaches have demonstrated strong performance but may struggle with generalization to unseen data. In contrast, training-free methods leverage powerful pre-trained models like Large Language Models (LLMs) to address various downstream tasks with only a few examples. Nonetheless, training-free methods for DIE encounter two primary challenges: (1) understanding the complex relationship between layout and textual elements in VRDs, and (2) providing accurate gu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17092","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.17092/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.17092","created_at":"2026-07-05T09:53:17.612789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17092v1","created_at":"2026-07-05T09:53:17.612789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17092","created_at":"2026-07-05T09:53:17.612789+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVS3DCC6MMIO","created_at":"2026-07-05T09:53:17.612789+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVS3DCC6MMIOOX3N","created_at":"2026-07-05T09:53:17.612789+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVS3DCC6","created_at":"2026-07-05T09:53:17.612789+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OVS3DCC6MMIOOX3NLEIS5V74PO","json":"https://pith.science/pith/OVS3DCC6MMIOOX3NLEIS5V74PO.json","graph_json":"https://pith.science/api/pith-number/OVS3DCC6MMIOOX3NLEIS5V74PO/graph.json","events_json":"https://pith.science/api/pith-number/OVS3DCC6MMIOOX3NLEIS5V74PO/events.json","paper":"https://pith.science/paper/OVS3DCC6"},"agent_actions":{"view_html":"https://pith.science/pith/OVS3DCC6MMIOOX3NLEIS5V74PO","download_json":"https://pith.science/pith/OVS3DCC6MMIOOX3NLEIS5V74PO.json","view_paper":"https://pith.science/paper/OVS3DCC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17092&json=true","fetch_graph":"https://pith.science/api/pith-number/OVS3DCC6MMIOOX3NLEIS5V74PO/graph.json","fetch_events":"https://pith.science/api/pith-number/OVS3DCC6MMIOOX3NLEIS5V74PO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVS3DCC6MMIOOX3NLEIS5V74PO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVS3DCC6MMIOOX3NLEIS5V74PO/action/storage_attestation","attest_author":"https://pith.science/pith/OVS3DCC6MMIOOX3NLEIS5V74PO/action/author_attestation","sign_citation":"https://pith.science/pith/OVS3DCC6MMIOOX3NLEIS5V74PO/action/citation_signature","submit_replication":"https://pith.science/pith/OVS3DCC6MMIOOX3NLEIS5V74PO/action/replication_record"}},"created_at":"2026-07-05T09:53:17.612789+00:00","updated_at":"2026-07-05T09:53:17.612789+00:00"}